Hierarchical Entity Typing via Multi-level Learning to Rank

We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.

[1]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[2]  Gerhard Weikum,et al.  HYENA: Hierarchical Type Classification for Entity Names , 2012, COLING.

[3]  Heng Ji,et al.  Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding , 2016, KDD.

[4]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.

[5]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[6]  Nevena Lazic,et al.  Context-Dependent Fine-Grained Entity Type Tagging , 2014, ArXiv.

[7]  Dan Roth,et al.  Entity Linking via Joint Encoding of Types, Descriptions, and Context , 2017, EMNLP.

[8]  Sheng Zhang,et al.  Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds , 2018, *SEMEVAL.

[9]  Yasumasa Onoe,et al.  Learning to Denoise Distantly-Labeled Data for Entity Typing , 2019, NAACL.

[10]  Kentaro Inui,et al.  An Attentive Neural Architecture for Fine-grained Entity Type Classification , 2016, AKBC@NAACL-HLT.

[11]  Yangqiu Song,et al.  Improving Fine-grained Entity Typing with Entity Linking , 2019, EMNLP/IJCNLP.

[12]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[13]  Ying Lin,et al.  An Attentive Fine-Grained Entity Typing Model with Latent Type Representation , 2019, EMNLP.

[14]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[15]  Kentaro Inui,et al.  Neural Architectures for Fine-grained Entity Type Classification , 2016, EACL.

[16]  Nevena Lazic,et al.  Embedding Methods for Fine Grained Entity Type Classification , 2015, ACL.

[17]  Gerhard Weikum,et al.  FINET: Context-Aware Fine-Grained Named Entity Typing , 2015, EMNLP.

[18]  Ashish Anand,et al.  Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings , 2017, EACL.

[19]  Tiansi Dong,et al.  Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks , 2019, EMNLP/IJCNLP.

[20]  Heng Ji,et al.  AFET: Automatic Fine-Grained Entity Typing by Hierarchical Partial-Label Embedding , 2016, EMNLP.

[21]  Olivier Raiman,et al.  DeepType: Multilingual Entity Linking by Neural Type System Evolution , 2018, AAAI.

[22]  Hinrich Schütze,et al.  Corpus-level Fine-grained Entity Typing Using Contextual Information , 2015, EMNLP.

[23]  Zhiyuan Liu,et al.  OpenKE: An Open Toolkit for Knowledge Embedding , 2018, EMNLP.

[24]  Omer Levy,et al.  Ultra-Fine Entity Typing , 2018, ACL.

[25]  Mo Yu,et al.  Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing , 2019, NAACL.

[26]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[27]  Andrew McCallum,et al.  Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking , 2018, ACL.

[28]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[29]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[30]  Jason Weston,et al.  Support vector machines for multi-class pattern recognition , 1999, ESANN.

[31]  Daniel S. Weld,et al.  Fine-Grained Entity Recognition , 2012, AAAI.